NVIDIA workshop: Generative AI with Diffusion Models
To view complete details for this event, click here to view the announcement
NVIDIA workshop: Generative AI with Diffusion Models
Thanks to improvements in computing power and scientific theory, Generative AI is more accessible than ever before. Generative AI will play a significant role across industries and will gain significant importance due to its numerous applications such as Creative Content Generation, Data Augmentation, Simulation and Planning, Anomaly Detection, Drug Discovery, and Personalized Recommendations etc. In this course we will take a deeper dive on denoising diffusion models, which are a popular choice for text-to-image pipelines, disrupting several industries.
Learning Objectives:
- Build a U-Net to generate images from pure noise
- Improve the quality of generated images with the Denoising Diffusion process
- Compare Denoising Diffusion Probabilistic Models (DDPMs) with Denoising Diffusion Implicit Models (DDIMs)
- Control the image output with context embeddings
- Generate images from English text-prompts using CLIP
Prerequisites:
- Good understanding of PyTorch
- Good understanding of deep learning
Technologies: PyTorch, CLIP
Hardware: Desktop or laptop computer capable of running the latest version of Chrome or Firefox. Each participant will be provided with dedicated access to a fully configured, GPU-accelerated workstation in the cloud.
Certificate: Upon successful completion of the assessment, participants will receive an NVIDIA DLI certificate to recognize their subject matter competency and support professional career growth.
Languages: English
Date and Time
- Date: 18 Oct 2024
- Time: 10:00 AM to 06:00 PM
- All times are (UTC+02:00) Ljubljana
Add Event to Calendar
Location
- This event has virtual attendance info. Please visit the event page to attend virtually.
Hosts
Registration
Speakers
Domen Verber
NVIDIA workshop: Generative AI with Diffusion Models
Jani Dugonik
NVIDIA workshop: Generative AI with Diffusion Models
Agenda
Meet the instructor.
Create an account at courses.nvidia.com/join
From U-Nets to Diffusion (60 mins)
Build a U-Net, a type of autoencoder for images.
Learn about transposed convolution to increase the size of an image.
Learn about non-sequential neural networks and residual connections.
Experiment with feeding noise through the U-Net to generate new images
Break (10 mins)
Learn how to alter the output of the diffusion process by adding context embeddings
Add additional model optimizations such as
Sinusoidal Position Embeddings
The GELU activation function
Attention
Text-to-Image with CLIP (60 minutes)
Walk through the CLIP architecture to learn how it associates image embeddings with text embeddings
Use CLIP to train a text-to-image diffusion model
Break (60 mins)
State-of-the-art Models (60 mins)
Review various state-of-the-art generative ai models and connect them to the concepts learned in class
Discuss prompt engineering and how to better influence the output of generative AI models
Learn about content authenticity and how to build trustworthy models
Final Review (60 mins)
Review key learnings and answer questions.
Complete the assessment and earn a certificate.
Complete the workshop survey.
Learn how to set up your own AI application development environment.
